Search

Nowadays, citrus fruits, especially oranges, is very important in the human nutrition regime, and its quality characteristics assessment is very important. This study aimed to predict some biochemical characteristics of blood orange, using machine vision and artificial neural networks. In this experiment, the amount of vitamin C content, sugar content, and acidity (pH) were obtained using destructive laboratory methods. Images of blood orange samples were captured and 108 texture features and 57 color features were extracted on CIElab, RGB, HSV, and HIS color spaces and finally, the artificial neural networks method has been used to estimate the desired properties. To evaluate and select the most optimal artificial neural network, a feed -forward neural networks with Levenberg -Marquardt learning algorithm, the different number of neurons, and different transfer functions in the hidden and output layers was used. Finally, using the best neural network and 165 textural -color features, the amount of vitamin C content, sugar content, and pH were estimated with a correlation coefficient of 0.950, 0.968, and 0.884, respectively. Therefore, considering the appropriate correlation coefficient, machine vision and image processing technology can estimate some biochemical characteristics of blood oranges accurately. [ABSTRACT FROM AUTHOR]

In the present study, in the first step, the effect of Aloe vera gel (75% v/v) coating containing different concentrations of hemp seed oil (1-5% v/v) on some physicochemical properties of cherry tomatoes during storage at room temperature was investigated. The results revealed the ability of hemp seed oil to improve the physicochemical properties of cherry tomatoes during storage, although no significant difference was observed between 3 and 5% levels of hemp seed oil (p> 0.05). Slope change in the ripening index trend occurred for A. vera gel (75% v/v) coated sample on day 12 and for A. vera gel containing 3% hemp seed oil coated sample on day 16. Using an image processing system, the changes of the coated samples were evaluated based on the color statistical and color texture features extracted from the images and were graded through different procedures. The results showed that the principal component analysis (PCA) and artificial neural network (ANN) methods were able to divide the cherry tomatoes into intact and blemished grades which the ANN method was graded samples using color texture features with higher accuracy (97.41%). The adaptive neuro-fuzzy inference system (ANFIS) method had higher diagnostic power than the other two methods and was able to grade the samples into three grades including intact, grade 2 and unusable with accuracy of 98.96%. [ABSTRACT FROM AUTHOR]